Translation Difficulty

When deciding on the use of machine translation, we may want to know beforehand the difficulty and hence expected quality for a given translation task.

Translation Difficulty is the main subject of 4 publications. 3 are discussed here.

Publications

The difficulty of translating a text may depend on many factors, such as source, genre, or dialect, some of which may be determined automatically (Kirchhoff et al., 2007). Birch et al. (2008) study the quality of machine translation systems for different language pairs, given the same domain of European Parliament proceedings. They find that the amount of reordering, the richness of target side morphology and language similarity are the main determining factors that make translation for a given language pair difficult. Koehn et al. (2009) extend this work to more languages and a different domain, and by using a more refined method to measure the degree of reordering.

Benchmarks

Discussion

Related Topics

Confidence Measures attempt to gauge if the produced output of a machine translation system is reliable.

New Publications

• van der Wees, Marlies and Bisazza, Arianna and Monz, Christof (2015): Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text, Proceedings of the Workshop on Noisy User-generated Text

  DELETEIntroduction   ResearchGroups   AvailableSoftware   SpeechTranslation   SignLanguage   ComputerAidedTranslation   OtherApproaches   Deployment Data   ParallelCorpora   ComparableCorpora   Dictionaries   CorpusCleaning   SentenceAlignment   Truecasing   WordSegmentation   SpellingCorrection   SparseData   PivotLanguages   DomainAdaptation WordBasedModels   IBMModels   Symmetrization   WordAlignment     WordAlignmentBasedOnCoocurrence     WordAlignmentWithLinguisticAnnotation     WordAlignmentForSyntaxBasedModels     DiscriminativeWordAlignment     WordAlignmentCombination     WordAlignmentEvaluation     AlignmentOfSubsententialUnits   DictionariesFromComparableCorpora   LexicalChoice   MTWithoutWordAlignment PhraseBasedModels   PhraseBasedModelTraining   PhraseBasedModelEM   PhraseBasedModelRefinement   ContextFeatures   Smoothing   Paraphrasing   PruningLargeModels   SuffixArrays   ReorderingModels   PhraseBasedVsEBMT SyntaxBasedModels   InversionTransductionGrammars   HierarchicalModels   StringToTree   TreeToString   TreeToTree   BinarizingSCFG   GenerativeSyntaxModels   DependencyStructure   DeepSyntax   ParseQuality   ParallelTreebanks   SyntacticCoherence LinguisticProblems   UnknownWords   Morphology   GeneratingRichMorphology   FactoredTranslationModels   Compounds   TranslatingTenseCaseMarkers   TranslatingChunksAndClauses   DocumentLevelAspects   Transliteration     TransliterationWithFSM     TransliterationWithOtherMethods     ForwardTransliteration     TransliterationTrainingData     IntegratingTransliteration   SyntacticPrereordering   POSChunkPrereordering   SyntacticReranking   IntegratingSyntacticFeatures LanguageModels   NGramLanguageModels   TargetedLanguageModels   MorphologicalLanguageModels   VeryLargeLanguageModels Decoding   StackDecoding   ReorderingConstraints   WordBasedDecoding   FiniteStateMachines   DecodingComplexity   SyntaxModelDecoding Evaluation   EvaluationCampaigns   ManualMetrics   TaskBasedMetrics   EditRateMetrics   NGramMetrics   SyntaxBasedMetrics   CorrelationOfMetrics   TrainedMetrics   TranslationDifficulty   StatisticalSignificance MachineLearning   WordGraphs   ParameterTuning   Reranking   LargeScaleDiscriminativeTraining   MinimumBayesRisk   ConfidenceMeasures   SystemCombination   IncrementalUpdating NeuralNetworkModels   NeuralLanguageModels   AttentionModel   Training   Inference   Coverage   Vocabulary   Embeddings   MultilingualWordEmbeddings   MonolingualData   Adaptation   LinguisticAnnotation   MultilingualMultimodalMultitask   AlternativeArchitectures   AnalysisAndVisualization   NeuralComponentsInStatisticalMachineTranslation add

  

  @InProceedings{vanderwees-bisazza-monz:2015:WNUT,
  author = {van der Wees, Marlies and Bisazza, Arianna and Monz, Christof},
  title = {Five Shades of Noise: Analyzing Machine Translation Errors in User-Generated Text},
  booktitle = {Proceedings of the Workshop on Noisy User-generated Text},
  month = {July},
  address = {Beijing, China},
  publisher = {Association for Computational Linguistics},
  pages = {28--37},
  url = {http://www.aclweb.org/anthology/W15-4304},
  year = 2015
  }
  Wees et al. (2015)